Forecasting the COVID-19 Space-time Dynamics in Brazil with Convolutional Graph Neural Networks and Transport Modals

One of the major challenges imposed by the SARS-CoV-2 pandemic is the lack of pattern in which the virus spreads, making it difficult to create effective policies to prevent and tackle the pandemic. Several approaches have been proposed to understand the virus behavior and anticipate its infection and death curves at country ans state levels, thus supporting containment measures. Those initiatives generalize well for general extents and decisions, but they do not predict so well the trajectory of the virus through specific regions, such as municipalities, considering their distinct interconnection profiles. Specially in countries with continental dimensions, like Brazil, too general decisions imply that containment measures are applied either too soon or too late. This study presents a novel scalable alternative to forecast the numbers of case and death by SARS-CoV-2, according to the influence that certain regions exert on others. By exploiting a single-model architecture of graph convolutional networks with recurrent networks, our approach maps the main access routes to municipalities in Brazil using the modals of transport, and processes this information via neural network algorithms to forecast at the municipal level ans for the whole country. We compared the performance in forecasting the pandemic daily numbers with three baseline models using Mean Absolute Error (MAE), Symmetric Mean Absolute Percentage Error (sMAPE) and Normalized Root Mean Square Error (NRMSE) metrics, with the forecasting horizon varying from 1 to 25 days. Results show that the proposed model overcomes the baselines when considering the MAE and NRMSE (p ˂0.01), being specially suitable for forecasts from 14 to 24 days ahead. Author

CHANGES IN TRANSPORT BEHAVIOUR OF THE CZECH POPULATION CAUSED BY STATE OF EMERGENCY

This article presents the results of an extensive questionnaire survey focused on changes in the transport behaviour of the population of the Czech Republic immediately after the government's announcement about the measures implemented to prevent the spread of COVID-19. The questionnaire aimed to determine the changes in the use of the mode of transport for regular travel to work, school, or for shopping, as well as to determine the changes in the frequency of these travels according to monitored socio-demographic groups of inhabitants and specified size groups of settlements. This article contains a statistical evaluation of these changes in the transport behaviour of the population using sophisticated statistical tools. A method is proposed for estimating the number of passengers in public transport using a linear regression model based on the data from conducted transport behaviour survey. In this paper, the Data envelopment analysis (hereinafter referred to as DEA method) within the case study in the South Bohemian Region is also used to determine whether the COVID-19 measures have reduced the efficiency of public transport.

COVID-19 and transportation of India: influence on infection risk and greenhouse gas emissions.

COVID-19 have significant impact on travel behaviour and greenhouse gases (GHG), especially for the most affected city in India, Mumbai metropolitan region (MMR). The present study attempts to explore the risk on different modes of transportation and GHG emissions (based on change in travel behavior) during peak/non-peak hours in a day by an online/offline survey for commuters in Indian metropolitan cities like MMR, Delhi and Bengaluru. In MMR, the probability of infection in car estimated to be 0.88 and 0.29 during peak and non-peak hour, respectively, considering all windows open. The risk of infection in public transportation system such as in bus (0.307), train (0.521), and metro (0.26) observed to be lower than in private vehicles. Furthermore, impact of COVID-19 on GHG emissions have also been explored considering three scenarios. The GHG emissions have been estimated for base (3.83-16.87 tonne), lockdown (0.22-0.48 tonne) and unlocking (2.13-9.30 tonne) scenarios. It has been observed that emissions are highest during base scenario and lowest during lockdown situation. This study will be a breakthrough in understanding the impact of pandemic on environment and transportation. The study shall help transport planners and decision makers to operate public transport during pandemic like situation such that the modal share of public transportation is always highest. It shall also help in regulating the GHG emissions causing climate change.